[run]
# What individual steps of HATCHet should we run in the pipeline?
# Valid values are True or False
download_panel = True
count_reads = True
genotype_snps = True
phase_snps = True
fixed_width = False  # True uses older fixed-width versions of some commands
count_alleles = True
combine_counts = True
cluster_bins = True
loc_clust = True  # True uses new locality-aware clustering
plot_bins = True
compute_cn = True
plot_cn = True

# What chromosome(s) do we wish to process in the pipeline? Leave unspecified to process
# all chromosomes found in the normal/tumor bam files
chromosomes =

# Path to reference genome
# Make sure you have also generated the reference dictionary as /path/to/reference.dict
reference = /path/to/reference.fa

# Make sure you have generated the .bam.bai files at the same locations as these bam files
normal = /path/to/normal.bam

# Space-delimited list of tumor BAM locations
bams = /path/to/tumor1.bam /path/to/tumor2.bam

# Space-delimited list of tumor names
samples = tumor1 tumor2

# Output path of the run script
output = output/

# How many cores to use for the end-end pipeline?
# This parameter, if specified, will override corresponding 'processes' parameters in individual <step> sections below.
processes = 6

[download_panel]
ref_panel = 1000GP_Phase3
refpaneldir = /path/to/reference/panel

[genotype_snps]
# Reference version used to select list of known germline SNPs;
# Possible values are "hg19" or "hg38", or leave blank "" if you wish for all positions to be genotyped by bcftools
reference_version = hg19
# Does your reference name chromosomes with "chr" prefix?; True or False
chr_notation = True

# Use 8 for WGS with >30x and 20 for WES with ~100x
mincov = 8
# Use 300 for WGS with >30x and Use 1000 for WES with ~100x
maxcov = 300
# Path to SNP list
#   If unspecified, HATCHet selects a list of known germline SNPs based on <run.reference_version> and <run.chr_notation>
#   If not, please provide full path to a locally stored list (.vcf.gz) here.
snps =

[combine_counts]
# Minimum number of SNP-covering reads per bin and sample
msr = 5000
# Minimum number of total reads per bin and sample
mtr = 5000

[cluster_bins_loc]
diploidbaf = 0.08
# Minimum and maximum number of clusters to infer
# (using silhouette score for model selection)
minK = 2
maxK = 30
# You can instead specify an exact number of clusters:
# exactK = 15

[plot_bins]
sizethreshold = 0.01
figsize = "6,3"

[compute_cn]
clones = 2,6
seeds = 400
minprop = 0.03
diploidcmax = 6
tetraploidcmax = 12
ghostprop = 0.35
limitinc = 0.6